Sparse Sampling for Adversarial Games
نویسندگان
چکیده
This paper introduces Monte Carlo *-Minimax Search (MCMS), a Monte-Carlo search algorithm for finite, turned based, stochastic, two-player, zero-sum games of perfect information. Through a combination of sparse sampling and classical pruning techniques, MCMS allows deep plans to be constructed. Unlike other popular tree search techniques, MCMS is suitable for densely stochastic games, i.e., games where one would never expect to sample the same state twice. We give a basis for the theoretical properties of the algorithm and evaluate its performance in three games: Pig (Pig Out), EinStein Würfelt Nicht!, and Can’t Stop.
منابع مشابه
Omputation and D Ecision - M Aking in L Arge E Xtensive F Orm G Ames
In this thesis, we investigate the problem of decision-making in large two-player zero-sumgames using Monte Carlo sampling and regret minimization methods. We demonstrate fourmajor contributions. The first is Monte Carlo Counterfactual Regret Minimization (MC-CFR): a generic family of sample-based algorithms that compute near-optimal equilibriumstrategies. Secondly, we develop a...
متن کاملMonte Carlo *-Minimax Search
This paper introduces Monte Carlo *-Minimax Search (MCMS), a Monte Carlo search algorithm for turned-based, stochastic, two-player, zero-sum games of perfect information. The algorithm is designed for the class of densely stochastic games; that is, games where one would rarely expect to sample the same successor state multiple times at any particular chance node. Our approach combines sparse sa...
متن کاملSampling Techniques for Zero-sum, Discounted Markov Games
In this paper, we first present a key approximation result for zero-sum, discounted Markov games, providing bounds on the state-wise loss and the loss in the sup norm resulting from using approximate Q-functions. Then we extend the policy rollout technique for MDPs to Markov games. Using our key approximation result, we prove that, under certain conditions, the rollout technique gives rise to a...
متن کاملOn Adversarial Search Spaces and Sampling-Based Planning
Upper Confidence bounds applied to Trees (UCT), a banditbased Monte-Carlo sampling algorithm for planning, has recently been the subject of great interest in adversarial reasoning. UCT has been shown to outperform traditional minimax based approaches in several challenging domains such as Go and Kriegspiel, although minimax search still prevails in other domains such as Chess. This work provide...
متن کاملRobust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks
Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...
متن کامل